SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.10853 · 2021

On the Importance of Environments in Human-Robot Coordination

arXiv · PDF · Open in the Atlas

Code that ran

9 of 12 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 3 failures of our instrument; 3 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2106.10853.json · badge: /api/ran/2106.10853.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
icaros-usc/overcooked_env_gen canonical (classifier label)
classifier basis: census
9 ran · 3 no recorded run
FunctionStatusWhere it lives
createRecordMap Ran
ran on a synthesized input
icaros-usc/overcooked_env_gen/overcooked_ai_pcg/LSI/gen_heat_map_2d.py
code served (permissive licence) · get_code("91f78898000d9b63")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# dataLabels: a list of strings that serve as keys for the output dictionary
dataLabels = ["feature_a", "feature_b", "feature_c"]

# recordList: a list of records where each record is indexable (like a tuple or list)
# and has elements corresponding to each label in dataLabels
recordList = [
    (1.0, 2.0, 3.0),
    (4.0, 5.0, 6.0),
]

ARGS = {
    "dataLabels": dataLabels,
    "recordList": recordList,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_agent_info Ran
ran on a synthesized input
icaros-usc/overcooked_env_gen/overcooked_ai_py/sample_trajectories.py
code served (permissive licence) · get_code("d5d071ee3485a58b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

# Create a simple stand-in class for held objects
class HeldObject:
    def __init__(self, name):
        self.name = name

# Create a simple stand-in class for agent
class Agent:
    def __init__(self, position, held_object=None):
        self.position = position
        self.held_object = held_object

# Initialize the dictionary that will be modified
t_obj = {}

# Create an agent with a position and a held object
agent = Agent(position=(2, 3), held_object=HeldObject('onion'))

# Define the agent_id
agent_id = 0

ARGS = {
    't_obj': t_obj,
    'agent': agent,
    'agent_id': agent_id
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
get_env_info Ran
ran on a synthesized input
icaros-usc/overcooked_env_gen/overcooked_ai_py/sample_trajectories.py
code served (permissive licence) · get_code("62e435f3cc324e62")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

class MockObjectState:
    def __init__(self, name, state):
        self.name = name
        self.state = state

class MockState:
    def __init__(self, objects=None, order_list=None):
        self.objects = objects
        self.order_list = order_list

class MockMDP:
    def __init__(self):
        pass
    
    def get_onion_dispenser_locations(self):
        return [(1, 2), (3, 4)]
    
    def get_pot_locations(self):
        return [(5, 6)]
    
    def get_dish_dispenser_locations(self):
        return [(7, 8), (9, 10)]
    
    def get_serving_locations(self):
        return [(11, 12)]

# Create test instances
t_obj = {}

state_objects = {
    'soup_1': MockObjectState('soup', (0, 2)),
    'soup_2': MockObjectState('soup', (0, 3)),
    'onion_1': MockObjectState('onion', (0, 0))
}
order_list = ['order1', 'order2', 'order3']
state = MockState(objects=state_objects, order_list=order_list)

mdp = MockMDP()

ARGS = {
    't_obj': t_obj,
    'state': state,
    'mdp': mdp
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
horizontal_flip Ran
ran on a synthesized input
icaros-usc/overcooked_env_gen/overcooked_ai_pcg/helper.py
code served (permissive licence) · get_code("d117a43767999260")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family int, shape (4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a simple 2D numpy array representing a game level
# Using shape (4, 3) - 4 rows, 3 columns with uint8 values
np_lvl = np.array([
    [1, 2, 3],
    [4, 5, 6],
    [7, 8, 9],
    [10, 11, 12]
], dtype=np.uint8)

ARGS = {
    "np_lvl": np_lvl
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family int, shape (4, 3) — shape (4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_dict_from_file Ran
ran; our contract draft was wrong, not the code
icaros-usc/overcooked_env_gen/overcooked_ai_py/utils.py
code served (permissive licence) · get_code("591c3a0919cdc129")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import os

# Create a temporary file with a dictionary representation
temp_dir = tempfile.mkdtemp()
filepath = os.path.join(temp_dir, "test_dict.py")

# Write a simple dictionary to the file
test_dict = {
    "key1": "value1",
    "key2": 42,
    "key3": [1, 2, 3],
    "key4": {"nested": "dict"}
}

with open(filepath, 'w') as f:
    f.write(repr(test_dict))

ARGS = {
    "filepath": filepath
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_dict_from_txt Ran
ran; our contract draft was wrong, not the code
icaros-usc/overcooked_env_gen/overcooked_ai_py/utils.py
code served (permissive licence) · get_code("1db1eb104270f970")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import tempfile
import os

# Create a temporary directory and file for testing
temp_dir = tempfile.mkdtemp()
temp_filepath = os.path.join(temp_dir, "test_config")

# Create a valid dict and write it to a .txt file
test_dict = {
    "model_name": "test_model",
    "learning_rate": 0.001,
    "batch_size": 32,
    "layers": [64, 128, 256],
    "use_dropout": True
}

# Write the dict to file with .txt extension
with open(temp_filepath + ".txt", "w") as f:
    f.write(str(test_dict))

# Define ARGS with the filename parameter (without .txt extension)
# The function will add .txt via fix_filetype
ARGS = {
    "filename": temp_filepath
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_pickle Ran
ran; our contract draft was wrong, not the code
icaros-usc/overcooked_env_gen/overcooked_ai_py/utils.py
code served (permissive licence) · get_code("451972971e39bedb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import io
import json
import pickle
import tempfile
import os

# Create a temporary directory and file for testing
temp_dir = tempfile.mkdtemp()
test_pickle_path = os.path.join(temp_dir, "test_file")

# Create a simple pickle file to load
test_data = {"key": "value", "number": 42, "list": [1, 2, 3]}
with open(test_pickle_path + ".pickle", "wb") as f:
    pickle.dump(test_data, f)

ARGS = {
    "filename": test_pickle_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
lvl_str2number Ran
ran on a synthesized input
icaros-usc/overcooked_env_gen/overcooked_ai_pcg/helper.py
code served (permissive licence) · get_code("61dd8147b8a382cb")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family float, shape (3, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

obj_types = '12XSPOD '

def lvl_str2number(raw_layout):
    """
    Turns pure string formatted lvl to num encoded format
    """
    np_lvl = np.zeros((len(raw_layout), len(raw_layout[0])))
    for x, row in enumerate(raw_layout):
        row = row.strip()
        for y, tile in enumerate(row):
            np_lvl[x, y] = obj_types.index(tile)
    return np_lvl

# Create a simple level layout as a list of strings
# Each string represents a row, containing characters from obj_types
raw_layout = [
    "12X ",
    "SPO ",
    "D12 "
]

ARGS = {
    "raw_layout": raw_layout
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (3, 4) — shape (3, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
vertical_flip Ran
ran on a synthesized input
icaros-usc/overcooked_env_gen/overcooked_ai_pcg/helper.py
code served (permissive licence) · get_code("fdfdf967fa7ca3a7")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned ndarray, ndim 2, dtype family int, shape (4, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np

# Create a small test level as a numpy array
# Using distinct dimensions (4 rows, 3 columns) for clarity
np_lvl = np.array([
    [1, 2, 3],
    [4, 5, 6],
    [7, 8, 9],
    [10, 11, 12]
], dtype=np.uint8)

ARGS = {
    "np_lvl": np_lvl
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family int, shape (4, 3) — shape (4, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
createRecordList Not yet run
unverified (harvested, no recorded run)
icaros-usc/overcooked_env_gen/overcooked_ai_pcg/LSI/gen_heat_map_2d.py
code served (permissive licence) · get_code("7d82d8619c93fa8c")
How it ran

no invocation recorded.

create_axes Not yet run
unverified (harvested, no recorded run)
icaros-usc/overcooked_env_gen/overcooked_ai_pcg/LSI/gen_heat_map.py
code served (permissive licence) · get_code("79fbd712a5a9f6ee")
How it ran

no invocation recorded.

csv_data_to_pandas Not yet run
unverified (harvested, no recorded run)
icaros-usc/overcooked_env_gen/overcooked_ai_pcg/LSI/gen_heat_map.py
code served (permissive licence) · get_code("d3635e9d05e031bd")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 9 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
load_dict_from_file 3 other papers
3 later
2302.04831 (2023-02)
Cooperative Open-ended Learning Framework for Zero-shot Coordination
2310.05208 (2023-10)
ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination
2502.20073 (2025-02)
Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents
load_dict_from_txt 3 other papers
3 later
2302.04831 (2023-02)
Cooperative Open-ended Learning Framework for Zero-shot Coordination
2310.05208 (2023-10)
ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination
2502.20073 (2025-02)
Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents
load_pickle 3 other papers
3 later
2302.04831 (2023-02)
Cooperative Open-ended Learning Framework for Zero-shot Coordination
2310.05208 (2023-10)
ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination
2502.20073 (2025-02)
Collab-Overcooked: Benchmarking and Evaluating Large Language Models as Collaborative Agents

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

When studying robots collaborating with humans, much of the focus has been on robot policies that coordinate fluently with human teammates in collaborative tasks. However, less emphasis has been placed on the effect of the environment on coordination behaviors. To thoroughly explore environments that result in diverse behaviors, we propose a framework for procedural generation of environments that are (1) stylistically similar to human-authored environments, (2) guaranteed to be solvable by the human-robot team, and (3) diverse with respect to coordination measures. We analyze the procedurally generated environments in the Overcooked benchmark domain via simulation and an online user study. Results show that the environments result in qualitatively different emerging behaviors and statistically significant differences in collaborative fluency metrics, even when the robot runs the same planning algorithm.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2106.10853")
get_code_for_paper("2106.10853")
have("2106.10853")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2106.10853.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2106.10853.svg)](https://syntology.ai/paper/2106.10853)

Connect an agent — have() is free.